RuntimeError:尝试在不构建函数的情况下捕获 EagerTensor [英] RuntimeError: Attempting to capture an EagerTensor without building a function
本文介绍了RuntimeError:尝试在不构建函数的情况下捕获 EagerTensor的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
我使用 tf.data.datset
API 并使用残差网络.当我为 TensorBoard 运行代码以可视化我的嵌入时,我遇到了这个错误,但是当我使用两层网络时,我没有这个问题.
I use tf.data.datset
API and use residual network. When I run code for TensorBoard for visualizing my embeddings I have this error, but when I use a two layers network I don't have this problem.
def load_and_preprocess_from_path_label(path, label):
return load_and_preprocess_image(path), label
ds = tf.data.Dataset.from_tensor_slices((all_image_paths, all_image_labels))
with tf.Session() as sess:
# TODO (@omoindrot): remove the hard-coded 10000
# Obtain the test labels
image_label_ds = ds.map(load_and_preprocess_from_path_label)
ds = image_label_ds.shuffle(image_count)
<小时>
RuntimeError Traceback (most recent call last)
<ipython-input-41-ead5d6a54baa> in <module>()
92 # TODO (@omoindrot): remove the hard-coded 10000
93 # Obtain the test labels
---> 94 image_label_ds = ds.map(load_and_preprocess_from_path_label)
95 ds = image_label_ds.shuffle(image_count)
96
RuntimeError: Attempting to capture an EagerTensor without building a function.
推荐答案
错误可能是Tensorflow版本问题
The error is possibly due to Tensorflow version
运行以下代码对我有用:
Running the following code worked for me:
import tensorflow.compat.v1 as tf
正确的功能:
tf.disable_v2_behavior()
这篇关于RuntimeError:尝试在不构建函数的情况下捕获 EagerTensor的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!
查看全文